AI Inference Platform SRE — Build Reliable Cloud Operations

BBG Ventures, LLC; Bellevue (WA); On-site; USD 133,000 - 220,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

401(k) plan

Life insurance

Wellbeing benefits

Paid holidays

Vacation days

Job summary

Alibaba Group's AI Inference Platform is seeking a Site Reliability Engineer to build and maintain a high-availability model service platform. You will oversee deployment, monitoring, and incident response while developing automation to ensure stability and scalability.

The role requires 3+ years in SRE/DevOps, expertise in Python/Golang/Java/C++, and fluency in Chinese and English. Experience with cloud-native architectures and Kubernetes is a plus.

Qualifications

• 3+ years of experience in SRE, DevOps, or backend development with distributed system operations.
• Proficiency in Python, Golang, Java, or C++.
• Strong ability to work under pressure, manage critical incidents, and participate in on-call rotations.
• Fluency in both Chinese and English for daily communication.

Responsibilities

• Oversee deployment, operation, and maintenance of the platform and website.
• Design and optimize monitoring, logging, and alerting to meet SLA targets.
• Investigate and resolve customer issues related to QoS of API services.
• Develop automation tools and diagnostic pipelines to improve stability and issue resolution.

Skills

Python

Golang

Java

C++

Cloud computing

Incident management

Bilingual (Chinese/English)

Tools

Kubernetes

Prometheus

Istio

Calico

Linux

Job description

Alibaba Group's AI Inference Platform is seeking a Site Reliability Engineer to build and maintain a high-availability model service platform. You will oversee deployment, monitoring, and incident response while developing automation to ensure stability and scalability.

The role requires 3+ years in SRE/DevOps, expertise in Python/Golang/Java/C++, and fluency in Chinese and English. Experience with cloud-native architectures and Kubernetes is a plus.